MemoryBuddy
Enables Hermes to store and recall user facts, preferences, and long-term context across sessions via a shared MCP memory server.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MemoryBuddyremember that I like coffee and prefer dark mode"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MemoryBuddy 🧠
Give your AI agents a shared memory that lasts. Deploy once, connect any MCP-compatible AI tool — Hermes, Trae, Cursor, Claude Desktop — they all share the same memory.
🌟 What is this?
Most AI tools suffer from "goldfish memory" — refresh the page, start a new session, switch to another app, and everything's gone. You keep reintroducing yourself, re-explaining your preferences, re-stating context.
MemoryBuddy fixes this with a shared memory layer that any AI tool can read from and write to:
🧠 Long-term memory — facts, preferences, decisions persist across sessions
🔍 Semantic search — find relevant memories by meaning, not just keywords
🤖 Auto fact extraction — LLM automatically distills what's worth remembering
📝 Smart summarization — long conversations get compressed, key points retained
🗑️ One-click forget —
DELETEwipes everything, GDPR compliant🔌 MCP protocol — any MCP-compatible client can connect, zero integration code
💸 $0/month — runs entirely on Cloudflare's free tier
Related MCP server: GroundMemory
💡 What problem does it solve?
😣 Without MemoryBuddy | ✅ With MemoryBuddy |
Every AI tool starts fresh — you re-explain yourself constantly | All your AI tools share one memory — tell one, they all know |
Switching from Hermes to Trae means losing all context | Switch freely — memory lives in the cloud, not in the tool |
AI forgets your preferences between sessions | Preferences persist forever, across all sessions and all tools |
Long conversations hit context limits | Auto-summarization keeps things compact |
Privacy concerns — can't delete what it remembers | One API call wipes everything, fully GDPR compliant |
🏗️ Architecture
┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐
│ Hermes │ │ Trae │ │ Cursor │ │ Claude │
└────┬────┘ └────┬────┘ └────┬────┘ └────┬────┘
│ MCP │ MCP │ MCP │ MCP
▼ ▼ ▼ ▼
┌──────────────────────────────────────────────────┐
│ MemoryBuddy Worker (Cloudflare) │
│ │
│ /mcp → MCP Server (5 tools, Streamable HTTP) │
│ /chat → HTTP API (SSE streaming + auto-extract)│
│ /memory/:userId → REST API │
└──────────┬──────────────────┬────────────────────┘
│ │
┌─────▼─────┐ ┌──────▼──────┐
│ D1 (facts)│ │ Vectorize │
│ SQLite DB │ │ (embeddings)│
└───────────┘ └─────────────┘Three-tier memory:
Short-term (Durable Object) — current conversation context
Long-term (D1 database) — structured facts: name, preferences, key entities
Semantic (Vectorize) — vector embeddings for meaning-based recall
🚀 Quick Start (3 steps, ~5 minutes)
Prerequisites
Cloudflare account (free is fine)
Node.js 18+
1. Clone & Install
git clone https://github.com/Trainspotting31/memory-buddy.git
cd memory-buddy
npm install2. Create Cloudflare Resources
npx wrangler login
# Create D1 database
npx wrangler d1 create memory-buddy-db
# Create Vectorize index
npx wrangler vectorize create memory-buddy-index --dimensions 768 --metric cosine
# Initialize database schema
npx wrangler d1 execute memory-buddy-db --remote --file=schema.sqlCopy the generated database_id into wrangler.toml (rename from wrangler.toml.example).
3. Deploy
npx wrangler deployDone! Your memory server is live at https://memory-buddy.<your-subdomain>.workers.dev 🎉
🔌 Connect Your AI Tools
MemoryBuddy speaks MCP (Model Context Protocol). Any MCP-compatible tool can connect — they all share the same memory.
Hermes Agent
hermes mcp add memory-buddy --url https://memory-buddy.<your-subdomain>.workers.dev/mcpTrae IDE
Settings → MCP → Add Manually
Type: Streamable HTTP
URL:
https://memory-buddy.<your-subdomain>.workers.dev/mcp
Or create .trae/mcp.json in your project:
{
"mcpServers": {
"memory-buddy": {
"type": "streamable-http",
"url": "https://memory-buddy.<your-subdomain>.workers.dev/mcp"
}
}
}Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"memory-buddy": {
"url": "https://memory-buddy.<your-subdomain>.workers.dev/mcp"
}
}
}Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"memory-buddy": {
"type": "streamable-http",
"url": "https://memory-buddy.<your-subdomain>.workers.dev/mcp"
}
}
}Any MCP Client (raw config)
Endpoint: https://memory-buddy.<your-subdomain>.workers.dev/mcp
Transport: Streamable HTTP
Auth: None (or add your own)🛠️ MCP Tools
Once connected, the AI gets 5 tools:
Tool | What it does | When AI calls it |
| Load all memory for a user | Start of conversation |
| Semantic search by meaning | "What did I say about X?" |
| Save a new fact | User shares preferences, decisions |
| Delete all memory | User says "forget everything" |
| List all memory spaces | Checking what exists |
Shared memory: All tools default to userId: "hermes-shared". Use different userIds to isolate memory per project/persona.
📡 HTTP API (no MCP needed)
POST /chat — Chat with memory
curl -N -X POST https://your-worker.workers.dev/chat \
-H "Content-Type: application/json" \
-d '{"userId":"user123","message":"Hi! I'm John and I love espresso."}'GET /memory/:userId — Get all memory
curl https://your-worker.workers.dev/memory/user123DELETE /memory/:userId — Wipe memory
curl -X DELETE https://your-worker.workers.dev/memory/user123GET /health — Health check
curl https://your-worker.workers.dev/health⚙️ Configuration
Edit wrangler.toml:
[vars]
LLM_MODEL = "@cf/meta/llama-3.2-3b-instruct" # Default: Workers AI (free)
# Optional: use external LLM instead of Workers AI
LLM_API_KEY = "sk-your-key"
LLM_API_BASE = "https://api.openai.com/v1"
LLM_MODEL = "gpt-4o-mini"💸 Why Cloudflare Free Tier?
Component | Free Tier | Self-Hosted Equivalent |
Compute (Workers) | 100K req/day | $5–$50/mo (VPS) |
Database (D1) | 1GB storage | $10–$100/mo (Postgres) |
Vector DB (Vectorize) | 256K vectors | $70+/mo (Pinecone) |
LLM (Workers AI) | 10K neurons/day | $10+/mo (API) |
Total | $0 | ~$100+/mo |
📁 Project Structure
memory-buddy/
├── src/
│ ├── index.ts # Hono router: /mcp + /chat + /memory + /health
│ ├── mcp.ts # MCP Server factory (5 tools, stateless)
│ ├── agent-do.ts # Durable Object: chat session + memory orchestration
│ ├── llm.ts # LLM abstraction (Workers AI / OpenAI-compatible)
│ └── memory/
│ ├── extract.ts # LLM-powered fact extraction
│ ├── retrieve.ts # Hybrid retrieval (D1 + Vectorize)
│ └── summarize.ts # Conversation summarization
├── public/index.html # Built-in demo chat UI
├── schema.sql # D1 database schema
├── wrangler.toml.example # Cloudflare config template
└── package.json🎮 Try the Demo
Open your Worker URL in a browser — you'll see a built-in chat interface.
Tell the agent your name and a preference ("I'm Sarah, I'm allergic to peanuts")
Refresh the page
Ask: "What do you know about me?"
It remembers everything. That's MemoryBuddy.
🗺️ Roadmap
MCP Server (Streamable HTTP)
Multi-agent shared memory
Semantic search
Auto fact extraction
Memory categories & filtering
User authentication
Batch memory import/export
Multi-language support
Hermes plugin (auto-inject memory at conversation start)
🤝 Contributing
Fork → 2. Branch → 3. Commit → 4. Push → 5. PR
📄 License
MIT — see LICENSE
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityBmaintenanceAn MCP server that extends AI agents' context window by providing tools to store, retrieve, and search memories, allowing agents to maintain history and context across long interactions.Last updatedMIT
- Alicense-qualityBmaintenanceAn MCP-native, local-first memory server that gives AI agents persistent, structured memory across sessions and tools, enabling them to maintain identity and context without reconfiguration.Last updated3MIT
- Flicense-qualityDmaintenanceA local MCP server that provides semantic memory storage and retrieval for coding and AI agents, enabling durable context across chat sessions.Last updated344
- AlicenseAqualityDmaintenanceMCP server for long-term agent memory, providing persistent memory, searchable knowledge, and evolving identity for AI agents.Last updated53Apache 2.0
Related MCP Connectors
Shared long-term memory vault for AI agents with 20 MCP tools.
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
Cloud-hosted MCP server for durable AI memory
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Trainspotting31/memory-buddy'
If you have feedback or need assistance with the MCP directory API, please join our Discord server